Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387390167> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4387390167 abstract "This paper introduces the T23 team's system submitted to the Singing Voice Conversion Challenge 2023. Following the recognition-synthesis framework, our singing conversion model is based on VITS, incorporating four key modules: a prior encoder, a posterior encoder, a decoder, and a parallel bank of transposed convolutions (PBTC) module. We particularly leverage Whisper, a powerful pre-trained ASR model, to extract bottleneck features (BNF) as the input of the prior encoder. Before BNF extraction, we perform pitch perturbation to the source signal to remove speaker timbre, which effectively avoids the leakage of the source speaker timbre to the target. Moreover, the PBTC module extracts multi-scale F0 as the auxiliary input to the prior encoder, thereby capturing better pitch variations of singing. We design a three-stage training strategy to better adapt the base model to the target speaker with limited target speaker data. Official challenge results show that our system has superior performance in naturalness, ranking 1st and 2nd respectively in Task 1 and 2. Further ablation justifies the effectiveness of our system design." @default.
- W4387390167 created "2023-10-06" @default.
- W4387390167 creator A5022760701 @default.
- W4387390167 creator A5033976028 @default.
- W4387390167 creator A5050219087 @default.
- W4387390167 creator A5058646669 @default.
- W4387390167 creator A5081164682 @default.
- W4387390167 date "2023-10-04" @default.
- W4387390167 modified "2023-10-07" @default.
- W4387390167 title "VITS-Based Singing Voice Conversion Leveraging Whisper and multi-scale F0 Modeling" @default.
- W4387390167 doi "https://doi.org/10.48550/arxiv.2310.02802" @default.
- W4387390167 hasPublicationYear "2023" @default.
- W4387390167 type Work @default.
- W4387390167 citedByCount "0" @default.
- W4387390167 crossrefType "posted-content" @default.
- W4387390167 hasAuthorship W4387390167A5022760701 @default.
- W4387390167 hasAuthorship W4387390167A5033976028 @default.
- W4387390167 hasAuthorship W4387390167A5050219087 @default.
- W4387390167 hasAuthorship W4387390167A5058646669 @default.
- W4387390167 hasAuthorship W4387390167A5081164682 @default.
- W4387390167 hasBestOaLocation W43873901671 @default.
- W4387390167 hasConcept C111919701 @default.
- W4387390167 hasConcept C118505674 @default.
- W4387390167 hasConcept C121332964 @default.
- W4387390167 hasConcept C134537474 @default.
- W4387390167 hasConcept C142362112 @default.
- W4387390167 hasConcept C149635348 @default.
- W4387390167 hasConcept C153083717 @default.
- W4387390167 hasConcept C153349607 @default.
- W4387390167 hasConcept C154945302 @default.
- W4387390167 hasConcept C2776539107 @default.
- W4387390167 hasConcept C2780513914 @default.
- W4387390167 hasConcept C28490314 @default.
- W4387390167 hasConcept C41008148 @default.
- W4387390167 hasConcept C558565934 @default.
- W4387390167 hasConcept C62520636 @default.
- W4387390167 hasConceptScore W4387390167C111919701 @default.
- W4387390167 hasConceptScore W4387390167C118505674 @default.
- W4387390167 hasConceptScore W4387390167C121332964 @default.
- W4387390167 hasConceptScore W4387390167C134537474 @default.
- W4387390167 hasConceptScore W4387390167C142362112 @default.
- W4387390167 hasConceptScore W4387390167C149635348 @default.
- W4387390167 hasConceptScore W4387390167C153083717 @default.
- W4387390167 hasConceptScore W4387390167C153349607 @default.
- W4387390167 hasConceptScore W4387390167C154945302 @default.
- W4387390167 hasConceptScore W4387390167C2776539107 @default.
- W4387390167 hasConceptScore W4387390167C2780513914 @default.
- W4387390167 hasConceptScore W4387390167C28490314 @default.
- W4387390167 hasConceptScore W4387390167C41008148 @default.
- W4387390167 hasConceptScore W4387390167C558565934 @default.
- W4387390167 hasConceptScore W4387390167C62520636 @default.
- W4387390167 hasLocation W43873901671 @default.
- W4387390167 hasOpenAccess W4387390167 @default.
- W4387390167 hasPrimaryLocation W43873901671 @default.
- W4387390167 hasRelatedWork W1524071955 @default.
- W4387390167 hasRelatedWork W1554502231 @default.
- W4387390167 hasRelatedWork W172797710 @default.
- W4387390167 hasRelatedWork W2029561777 @default.
- W4387390167 hasRelatedWork W2945105049 @default.
- W4387390167 hasRelatedWork W2948317131 @default.
- W4387390167 hasRelatedWork W3165080709 @default.
- W4387390167 hasRelatedWork W4288365855 @default.
- W4387390167 hasRelatedWork W4387098302 @default.
- W4387390167 hasRelatedWork W2500371832 @default.
- W4387390167 isParatext "false" @default.
- W4387390167 isRetracted "false" @default.
- W4387390167 workType "article" @default.